INDEX

Explanations

elements of legal terminology and their implications

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãģ¸ãģ¨

-0.15

 Bunlar

-0.15

olian

-0.14

 ëĵ±ìĿĦ

-0.13

 Yine

-0.13

ÑħÐ¸

-0.13

ader

-0.12

unge

-0.12

isay

-0.12

ãģĵãģĿ

-0.12

POSITIVE LOGITS

 because

1.17

because

1.06

 porque

0.92

Because

0.88

 Because

0.88

åĽłä¸º

0.86

ï¼ĮåĽłä¸º

0.79

 karena

0.78

ecause

0.75

 omdat

0.75

Activations Density 2.741%

elements of legal terminology and their implications

No Comments

No Known Activations